# Towards Privacy-preserving Explanations in Medical Image Analysis

arXiv: https://arxiv.org/abs/2107.09652 · HTML: https://mlsanity.com/paper/2107.09652/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 26 references that are in the map.
- First posted on arXiv 20 Jul 2021.

## Builds on (most cited first, 12 of 12)

- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions](https://mlsanity.com/paper/1710.04806/) (2017)
- [Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning](https://mlsanity.com/paper/1803.04765/) (2018)
- [Towards Explainable Deep Neural Networks (xDNN)](https://mlsanity.com/paper/1912.02523/) (2019)
- [iNNvestigate neural networks!](https://mlsanity.com/paper/1808.04260/) (2018)
- [Assessment of iris recognition reliability for eyes affected by ocular pathologies](https://mlsanity.com/paper/1809.00206/) (2018)
- [VGAN-Based Image Representation Learning for Privacy-Preserving Facial Expression Recognition](https://mlsanity.com/paper/1803.07100/) (2018)
- [Real or Not Real, that is the Question](https://mlsanity.com/paper/2002.05512/) (2020)
- [Siamese Generative Adversarial Privatizer for Biometric Data](https://mlsanity.com/paper/1804.08757/) (2018)
- [Implications of Ocular Pathologies for Iris Recognition Reliability](https://mlsanity.com/paper/1809.00168/) (2018)

## Built on by (most cited first, 2 of 2)

- [Anonymizing medical case-based explanations through disentanglement](https://mlsanity.com/paper/2311.04833/) (2023)
- [Deep Aesthetic Assessment and Retrieval of Breast Cancer Treatment Outcomes](https://mlsanity.com/paper/2205.12611/) (2022)

## Abstract (arXiv)

The use of Deep Learning in the medical field is hindered by the lack of interpretability. Case-based interpretability strategies can provide intuitive explanations for deep learning models' decisions, thus, enhancing trust. However, the resulting explanations threaten patient privacy, motivating the development of privacy-preserving methods compatible with the specifics of medical data. In this work, we analyze existing privacy-preserving methods and their respective capacity to anonymize medical data while preserving disease-related semantic features. We find that the PPRL-VGAN deep learning method was the best at preserving the disease-related semantic features while guaranteeing a high level of privacy among the compared state-of-the-art methods. Nevertheless, we emphasize the need to improve privacy-preserving methods for medical imaging, as we identified relevant drawbacks in all existing privacy-preserving approaches.